Editing Boolean Classifiers: A Belief Change Perspective

Nicolas Schwind, Katsumi Inoue, Pierre Marquis

AAAI 2023 pp. 6516-6524

doi:10.1609/AAAI.V37I5.25801 /aaai/2023/schwind2023aaai-editing/

Abstract

This paper is about editing Boolean classifiers, i.e., determining how a Boolean classifier should be modified when new pieces of evidence must be incorporated. Our main goal is to delineate what are the rational ways of making such edits. This goes through a number of rationality postulates inspired from those considered so far for belief revision. We give a representation theorem and present some families of edit operators satisfying the postulates.

PDF AAAI Semantic Scholar

Cite

Text

Schwind et al. "Editing Boolean Classifiers: A Belief Change Perspective." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I5.25801

Markdown

[Schwind et al. "Editing Boolean Classifiers: A Belief Change Perspective." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/schwind2023aaai-editing/) doi:10.1609/AAAI.V37I5.25801

BibTeX

@inproceedings{schwind2023aaai-editing,
  title     = {{Editing Boolean Classifiers: A Belief Change Perspective}},
  author    = {Schwind, Nicolas and Inoue, Katsumi and Marquis, Pierre},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {6516-6524},
  doi       = {10.1609/AAAI.V37I5.25801},
  url       = {https://mlanthology.org/aaai/2023/schwind2023aaai-editing/}
}